Back

MASIv2 enables standardization and integration of multi-modal single-cell and spatial omics data with one general framework

Xu, Y.; Hayat, S.

2023-05-18 bioinformatics
10.1101/2023.05.15.540808 bioRxiv
Show abstract

Data annotation and integration are two common tasks in large-scale and collaborative single-cell research. Rapid technological advancements have made diverse single-cell and spatial data modalities available. This data deluge brought up great challenges in data annotation and integration. Though different biological modalities preserve shared features to define the same cellular system, they often present unique angles to unravel a multi-level understanding about this system. Here, we present one general framework that uses modality-shared and -specific features for annotation and integration of single-cell and spatial omics data. We benchmark our framework with existing methods across different datasets and demonstrate its application in two real world tasks.

Matching journals

The top 1 journal accounts for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.